Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    to or for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    د
    0.80
    我有
    0.75
    대
    0.74
    一
    0.73
    ח
    0.73
    える
    0.72
    つ
    0.68
    増
    0.67
    ผม
    0.66
     אם
    0.66
    POSITIVE LOGITS
     comulti
    0.77
     ഗവേഷ
    0.73
    ból
    0.73
     ferrug
    0.72
    0.68
     phytochemical
    0.68
    графии
    0.66
    ificados
    0.65
    ूटूथ
    0.65
     cartes
    0.65
    Act Density 0.000%

    No Known Activations